{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:44:29Z","timestamp":1778085869319,"version":"3.51.4"},"reference-count":33,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1016\/j.neucom.2019.01.109","type":"journal-article","created":{"date-parts":[[2019,4,24]],"date-time":"2019-04-24T11:25:58Z","timestamp":1556105158000},"page":"216-223","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":33,"special_numbering":"C","title":["Nash Q-learning based equilibrium transfer for integrated energy management game with We-Energy"],"prefix":"10.1016","volume":"396","author":[{"given":"Lingxiao","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuye","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dazhong","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-7002-9800","authenticated-orcid":false,"given":"Qinglai","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.neucom.2019.01.109_bib0001","doi-asserted-by":"crossref","first-page":"3006","DOI":"10.1109\/TSG.2015.2412779","article-title":"A multiagent-based consensus algorithm for distributed coordinated control of distributed generators in the energy internet","volume":"6","author":"Sun","year":"2015","journal-title":"IEEE Trans. Smart Grid"},{"issue":"1","key":"10.1016\/j.neucom.2019.01.109_bib0002","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.automatica.2010.10.033","article-title":"An iterative adaptive dynamic programming method for solving a class of nonlinear zero-sum differential games","volume":"47","author":"Zhang","year":"2011","journal-title":"Automatica"},{"issue":"3","key":"10.1016\/j.neucom.2019.01.109_bib0003","doi-asserted-by":"crossref","first-page":"4255","DOI":"10.1109\/TIE.2016.2532842","article-title":"Contribution-based energy-trading mechanism in microgrids for future smart grid: a game theoretic approach","volume":"67","author":"Park","year":"2016","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"1","key":"10.1016\/j.neucom.2019.01.109_bib0004","doi-asserted-by":"crossref","first-page":"195206","DOI":"10.1109\/TPWRS.2003.820692","article-title":"Numerical solutions to Nash\u2013Cournot equilibria in coupled constraint electricity markets","volume":"19","author":"Contreras","year":"2004","journal-title":"IEEE Trans. Power Syst."},{"issue":"7","key":"10.1016\/j.neucom.2019.01.109_bib0005","doi-asserted-by":"crossref","first-page":"12191234","DOI":"10.1109\/JSAC.2013.130706","article-title":"Bidirectional energy trading and residential load scheduling with electric vehicles in the smart grid","volume":"31","author":"Kim","year":"2013","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"10.1016\/j.neucom.2019.01.109_bib0006","doi-asserted-by":"crossref","first-page":"1720","DOI":"10.1109\/TNNLS.2015.2461491","article-title":"Adaptive portfolio optimization for multiple electricity markets participation","volume":"27","author":"Pinto","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"12","key":"10.1016\/j.neucom.2019.01.109_bib0007","doi-asserted-by":"crossref","first-page":"2999","DOI":"10.1049\/iet-gtd.2016.0024","article-title":"Non-cooperative game theory based energy management systems for energy district in the retail market considering DER uncertainties","volume":"10","author":"Marzband","year":"2016","journal-title":"Iet Gener. Transm. Distrib."},{"issue":"119","key":"10.1016\/j.neucom.2019.01.109_bib0008","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/j.apenergy.2014.01.003","article-title":"A game theoretic framework for a next-generation retail electricity market with high penetration of distributed residential electricity suppliers","volume":"119","author":"Su","year":"2014","journal-title":"Appl. Energy"},{"issue":"2","key":"10.1016\/j.neucom.2019.01.109_bib0009","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1109\/TSG.2014.2377020","article-title":"Integrated demand side management game in smart energy hubs","volume":"6","author":"Sheikhi","year":"2015","journal-title":"IEEE Trans. Smart Grid"},{"issue":"2","key":"10.1016\/j.neucom.2019.01.109_bib0010","first-page":"650","article-title":"From demand response in smart grid toward integrated demand response in smart energy hub","volume":"7","author":"Bahrami","year":"2016","journal-title":"IEEE Trans. Smart Grid"},{"key":"10.1016\/j.neucom.2019.01.109_bib0011","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.ijepes.2016.01.044","article-title":"Optimal planning and scheduling of energy hub in presence of wind, storage and demand response under uncertainty","volume":"80","author":"Pazouki","year":"2016","journal-title":"Int. J. Electr. Power"},{"issue":"7","key":"10.1016\/j.neucom.2019.01.109_bib0012","doi-asserted-by":"crossref","first-page":"5468","DOI":"10.1109\/TIE.2017.2674581","article-title":"Adaptive dynamic programming-based optimal control scheme for energy storage systems with solar renewable energy","volume":"42","author":"Wei","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"issue":"12","key":"10.1016\/j.neucom.2019.01.109_bib0013","doi-asserted-by":"crossref","first-page":"2226","DOI":"10.1109\/TNN.2011.2168538","article-title":"Data-driven robust approximate optimal tracking control for unknown general nonlinear systems using adaptive dynamic programming method","volume":"22","author":"Zhang","year":"2011","journal-title":"IEEE Trans. Neural Netw."},{"issue":"10","key":"10.1016\/j.neucom.2019.01.109_bib0014","doi-asserted-by":"crossref","first-page":"45894602","DOI":"10.1109\/TVT.2014.2374237","article-title":"Learning based frequency and time-domain inter-cell interference coordination in hetnets","volume":"64","author":"Simsek","year":"2015","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"1","key":"10.1016\/j.neucom.2019.01.109_bib0015","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/TNN.2007.900227","article-title":"Generalized Hamilton Jacobi Bellman formulation-based neural network control of affine nonlinear discrete-time systems","volume":"19","author":"Chen","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"issue":"5","key":"10.1016\/j.neucom.2019.01.109_bib0016","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1109\/TSMC.2015.2478885","article-title":"Fault-tolerant controller design for a class of nonlinear MIMO discrete-time systems via online reinforcement learning algorithm","volume":"46","author":"Wang","year":"2016","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"5","key":"10.1016\/j.neucom.2019.01.109_bib0017","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1109\/TCYB.2016.2542923","article-title":"Discrete-time deterministic q -learning: a novel convergence analysis","volume":"47","author":"Wei","year":"2017","journal-title":"IEEE Trans. Cybern."},{"issue":"6","key":"10.1016\/j.neucom.2019.01.109_bib0018","doi-asserted-by":"crossref","first-page":"2179","DOI":"10.1109\/TNNLS.2018.2810138","article-title":"Optimal fault-tolerant control for discrete-time nonlinear strict-feedback systems based on adaptive critic design","volume":"29","author":"Wang","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2019.01.109_bib0019","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.automatica.2018.06.051","article-title":"Unified iterative learning control for flexible structures with input constraints","volume":"962","author":"He","year":"2018","journal-title":"Automatica"},{"issue":"12","key":"10.1016\/j.neucom.2019.01.109_bib0020","doi-asserted-by":"crossref","first-page":"3083","DOI":"10.1109\/TNNLS.2015.2403394","article-title":"Emotional multiagent reinforcement learning in spatial social dilemmas","volume":"26","author":"Yu","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2019.01.109_bib0021","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.neucom.2016.08.108","article-title":"Path planning of multi-agent systems in unknown environment with neural kernel smoothing and reinforcement learning","volume":"233","author":"Cruz","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2019.01.109_bib0022","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","article-title":"Multi-agent reinforcement learning as a rehearsal for decentralized planning","volume":"190","author":"Kraemer","year":"2016","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2019.01.109_bib0023","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.neucom.2015.06.066","article-title":"Reinforcement learning-based asymptotic cooperative tracking of a class multi-agent dynamic systems using neural networks","volume":"171","author":"Cui","year":"2016","journal-title":"Neurocomputing"},{"issue":"6","key":"10.1016\/j.neucom.2019.01.109_bib0024","doi-asserted-by":"crossref","first-page":"1742","DOI":"10.1109\/TSMCC.2012.2218596","article-title":"Multiagent-based reinforcement learning for optimal reactive power dispatch","volume":"42","author":"Xu","year":"2012","journal-title":"IEEE Trans. Syst. Man Cybern."},{"issue":"4","key":"10.1016\/j.neucom.2019.01.109_bib0025","doi-asserted-by":"crossref","first-page":"1669","DOI":"10.1109\/TPWRS.2014.2357079","article-title":"Multi-agent correlated equilibrium q(\u03bb) learning for coordinated smart generation control of interconnected power grids","volume":"30","author":"Yu","year":"2015","journal-title":"IEEE Trans. Power Syst."},{"key":"10.1016\/j.neucom.2019.01.109_bib0026","series-title":"Proceedings of International Conference on Machine Learning","first-page":"242","article-title":"Multiagent reinforcement learning: theoretical framework and an algorithm","author":"Hu","year":"1998"},{"key":"10.1016\/j.neucom.2019.01.109_bib0027","series-title":"Proceedings of Conference on International Conference on Machine Learning","first-page":"157","article-title":"Markov games as a framework for multi-agent reinforcement learning","author":"Littman","year":"1994"},{"key":"10.1016\/j.neucom.2019.01.109_bib0028","first-page":"16331685","article-title":"Transfer learning for reinforcement learning domains: a survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"10.1016\/j.neucom.2019.01.109_bib0029","doi-asserted-by":"crossref","first-page":"347351","DOI":"10.2307\/1911749","article-title":"Existence and uniqueness of equilibrium points for concaven-person games","volume":"33","author":"Rosen","year":"1965","journal-title":"Econometrica"},{"issue":"4","key":"10.1016\/j.neucom.2019.01.109_bib0030","first-page":"1039","article-title":"Nash q-learning for general-sum stochastic games","volume":"4","author":"Wellman","year":"2003","journal-title":"J. Mach. Learn. Res."},{"issue":"5","key":"10.1016\/j.neucom.2019.01.109_bib0031","first-page":"1031","article-title":"Optimized data fusion for kernel k-means clustering","volume":"34","author":"Yu","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.neucom.2019.01.109_bib0032","doi-asserted-by":"crossref","first-page":"642662","DOI":"10.1016\/j.geb.2006.03.015","article-title":"Simple search methods for finding a nash equilibrium","volume":"63","author":"Porter","year":"2008","journal-title":"Games Econ. Behav."},{"issue":"7","key":"10.1016\/j.neucom.2019.01.109_bib0033","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1109\/TCYB.2014.2349152","article-title":"Accelerating multiagent reinforcement learning by equilibrium transfer","volume":"45","author":"Hu","year":"2014","journal-title":"IEEE Trans. Cybern."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0925231219304357?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0925231219304357?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T19:06:14Z","timestamp":1760382374000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231219304357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":33,"alternative-id":["S0925231219304357"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.neucom.2019.01.109","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2020,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Nash Q-learning based equilibrium transfer for integrated energy management game with We-Energy","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.neucom.2019.01.109","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2019 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}